Jaehong Oh

Dr. Jaehong Oh

Korea Maritime and Ocean University, Busan 49112, Korea
orcid

Research Focus & Metrics

Academic Career Length

22Years (2005-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2010 in Photogrammetric Engineering & Remote Sensing
Verified
Journal Article
Closed access
Jaehong OhJaehong Oh
Jaehong Oh
WLWon Hee Lee
Won Hee Lee
CTCharles K. Toth
Charles K. Toth
DGDorota A. Grejner-Brzezinska
Dorota A. Grejner-Brzezinska
CLChangno Lee
Changno Lee

1 February 2015 in ISPRS Journal of Photogrammetry and Remote Sensing
Verified
Journal Article
Closed access
Jaehong OhJaehong Oh
Jaehong Oh
CLChangno Lee
Changno Lee

31 August 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
AJAisha Javed
Aisha Javed
TKTaeheon Kim
Taeheon Kim
CLChanghui Lee
Changhui Lee
Jaehong OhJaehong Oh
Jaehong Oh
Youkyung HanYoukyung Han
Youkyung Han
Urban forests globally face severe degradation due to human activities and natural disasters, making deforestation an urgent environmental challenge. Remote sensing technology and very-high-resolution (VHR) bitemporal satellite imagery enable change detection (CD) for monitoring forest changes. However, deep learning techniques for forest CD concatenate bitemporal images into a single input, limiting the extraction of informative deep features from individual raw images. Furthermore, they are developed for middle to low-resolution images focused on specific forests such as the Amazon or a single element in the urban environment. Therefore, in this study, we propose deep learning-based urban forest CD along with overall changes in the urban environment by using VHR bitemporal images. Two networks are used independently: DeepLabv3+ for generating binary forest cover masks, and a deeply supervised image fusion network (DSIFN) for the generation of a binary change mask. The results are concatenated for semantic CD focusing on forest cover changes. To carry out the experiments, full scene tests were performed using the VHR bitemporal imagery of three urban cities acquired via three different satellites. The findings reveal significant changes in forest covers alongside urban environmental changes. Based on the accuracy assessment, the networks used in the proposed study achieved the highest F1-score, kappa, IoU, and accuracy values compared with those using other techniques. This study contributes to monitoring the impacts of climate change, rapid urbanization, and natural disasters on urban environments especially urban forests, as well as relations between changes in urban environment and urban forests.

7 October 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
CLChanghui Lee
Changhui Lee
SPSeonyoung Park
Seonyoung Park
TKTaeheon Kim
Taeheon Kim
Sicong LiuSicong Liu
Sicong Liu
MRMohd Nadzri Md Reba
Mohd Nadzri Md Reba
Youkyung HanYoukyung Han
Youkyung Han
Recently, an increase in wildfire incidents has caused significant damage from economical, humanitarian, and environmental perspectives. Wildfires have increased in severity, frequency, and duration because of climate change and rising global temperatures, resulting in the release of massive volumes of greenhouse gases, the destruction of forests and associated habitats, and the damage to infrastructures. Therefore, identifying burned areas is crucial for monitoring wildfire damage. In this study, we aim at detecting forest burned areas occurring in South Korea using optical satellite images. To exploit the advantage of applying machine learning, the present study employs representative three machine learning methods, Light Gradient Boosting Machine (LightGBM), Random Forest (RF), and U-Net, to detect forest burned areas with a combination of input variables, namely Surface Reflectance (SR), Normalized Difference Vegetation Index (NDVI), and Normalized Burn Ratio (NBR). Two study sites of recently occurred forest fire events in South Korea were selected, and Sentinel-2 satellite images were used by considering a small scale of the forest fires. The quantitative and qualitative evaluations according to the machine learning methods and input variables were carried out. In terms of the comparison focusing on machine learning models, the U-Net showed the highest accuracy in both sites amongst the designed variants. The pre and post fire images by SR, NDVI, NBR, and difference of indices as the main inputs showed the best result. We also demonstrated that diverse landcovers may result in a poor burned area detection performance by comparing the results of the two sites.

29 September 2017 in Sensors
Verified
Journal Article
Open access
PDF file
Jaehong OhJaehong Oh
Jaehong Oh
CLChangno Lee
Changno Lee
Power lines are cables that carry electrical power from a power plant to an electrical substation. They must be connected between the tower structures in such a way that ensures minimum tension and sufficient clearance from the ground. Power lines can stretch and sag with the changing weather, eventually exceeding the planned tolerances. The excessive sags can then cause serious accidents, while hindering the durability of the power lines. We used photogrammetric techniques with a low-cost drone to achieve efficient 3D mapping of power lines that are often difficult to approach. Unlike the conventional image-to-object space approach, we used the object-to-image space approach using cubic grid points. We processed four strips of aerial images to automatically extract the power line points in the object space. Experimental results showed that the approach could successfully extract the positions of the power line points for power line generation and sag measurement with the elevation accuracy of a few centimeters.

28 July 2014 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
CLChangno Lee
Changno Lee
Jaehong OhJaehong Oh
Jaehong Oh
CHChanghee Hong
Changhee Hong
JYJunhee Youn
Junhee Youn
The automated generation of a digital elevation model over the Antarctic using stereo matching high-resolution satellite images is a challenging task. Moreover, the homogeneous radiometry in the icy environment and the strong geometric dissimilarity between stereo pairs over the steep terrain limit the use of area-based matching techniques. To overcome this issue, we propose template matching with image transformation in order to reduce the geometric dissimilarity. First, we generated epipolar resampled images to ensure the ease of estimation and handling of image dissimilarities from various viewing directions. We then utilized the normalized cross-correlation (NCC) and transformed the image patches within the matching window along the sample, line, and diagonal directions in order to improve the match rates within the steep areas. Furthermore, we tested the proposed method using Antarctic IKONOS stereo images and found that the overall matching success rate improved from 93.5% to 97.0% for all image pixels. We then computed the success rates over an area in which the NCC produced a low elevation point density and observed a more significant improvement from 58.7% to 79.26%. When compared to the manually generated elevation, the maximum vertical difference improved from 11.4 to 4.7 m. With these improvements, we can build a 1-m resolution elevation model over the glaciated high relief terrain.